INDEX

Explanations

the word "that" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dit

-0.15

 identity

-0.14

ictor

-0.14

itez

-0.14

 lady

-0.14

 comparison

-0.14

crit

-0.13

wal

-0.13

ihn

-0.13

FP

-0.13

POSITIVE LOGITS

hlas

0.17

();)

0.15

à¥ĭà¤·

0.15

iko

0.14

CurrentValue

0.14

amodel

0.14

.rdf

0.14

ãĥ³ãĥĨãĤ£

0.14

Ð½ÐµÐ½

0.14

ORIZ

0.14

Activations Density 0.036%

the word "that" in various contexts

No Comments

No Known Activations